nttx commited on
Commit
7c07398
·
verified ·
1 Parent(s): b19fbfe

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d698e73b690c75a40575b7bb808052d4c6ffa3cdf0f56776d2ecc42555efd8
3
  size 226530600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5762c3376d4dc9933ecf5c4a13fdad9ee0edaa63ef03b7a8ecf78656159249fc
3
  size 226530600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840bcf99ceb7dced7fd006c5d67e48fd526e470ec15a1cdbca3bc4aafbd3dd5b
3
  size 453227642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a1833964d7f7c621c2c988d7e7533b396f17454bdac17940b808df3233ae7d
3
  size 453227642
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cfac906ffd1fafa858f035d56587459952647ee81f3a1e68453cbea34d3fd23
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c59ed076d9fae8b8c18f86e75c5879ebae38f3891655bbaaea513926673d8f26
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.4274191856384277,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013392259274139548,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 29.391,
374
  "eval_steps_per_second": 3.674,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.5690224772317184e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.29975962638855,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.026784518548279096,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 29.391,
374
  "eval_steps_per_second": 3.674,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013660104459622338,
379
+ "grad_norm": 1.1778364181518555,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 1.5307,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01392794964510513,
386
+ "grad_norm": 1.1236673593521118,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.426,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.01419579483058792,
393
+ "grad_norm": 1.260818362236023,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.3402,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01446364001607071,
400
+ "grad_norm": 1.085547924041748,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.5018,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.014731485201553502,
407
+ "grad_norm": 1.1603915691375732,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.4967,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.014999330387036294,
414
+ "grad_norm": 0.8015130162239075,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.5755,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.015267175572519083,
421
+ "grad_norm": 0.7664585113525391,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.5385,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.015535020758001875,
428
+ "grad_norm": 0.8574821352958679,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.6405,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.015802865943484665,
435
+ "grad_norm": 0.8299852013587952,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.776,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.016070711128967456,
442
+ "grad_norm": 0.8474833369255066,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.7013,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.016338556314450248,
449
+ "grad_norm": 0.8854416608810425,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.9526,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01660640149993304,
456
+ "grad_norm": 0.768135666847229,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.9447,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01687424668541583,
463
+ "grad_norm": 0.7588602304458618,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.9295,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.017142091870898622,
470
+ "grad_norm": 0.6751791834831238,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.7876,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.01740993705638141,
477
+ "grad_norm": 0.6478527188301086,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.9363,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.017677782241864202,
484
+ "grad_norm": 0.6559606194496155,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.9391,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.017945627427346993,
491
+ "grad_norm": 0.744279682636261,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.9356,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.018213472612829785,
498
+ "grad_norm": 0.6772345900535583,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 1.9644,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.018481317798312576,
505
+ "grad_norm": 0.7138044238090515,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 2.1931,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.018749162983795368,
512
+ "grad_norm": 0.6352837681770325,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 2.1747,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.019017008169278156,
519
+ "grad_norm": 0.6459941864013672,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 2.1023,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.019284853354760947,
526
+ "grad_norm": 0.7353226542472839,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 2.155,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01955269854024374,
533
+ "grad_norm": 0.7858691215515137,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 2.2813,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01982054372572653,
540
+ "grad_norm": 0.7619921565055847,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 2.204,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020088388911209322,
547
+ "grad_norm": 0.7330780029296875,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 2.2396,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.020356234096692113,
554
+ "grad_norm": 0.8096740245819092,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 2.2636,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0206240792821749,
561
+ "grad_norm": 0.7232469916343689,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 2.3257,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.020891924467657693,
568
+ "grad_norm": 0.6932474970817566,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 2.3433,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021159769653140485,
575
+ "grad_norm": 0.7939447164535522,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 2.3939,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.021427614838623276,
582
+ "grad_norm": 0.8171970844268799,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 2.4782,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.021695460024106068,
589
+ "grad_norm": 0.8745401501655579,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 2.5777,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02196330520958886,
596
+ "grad_norm": 0.7955912351608276,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 2.6236,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.022231150395071647,
603
+ "grad_norm": 0.8104299306869507,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 2.6135,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02249899558055444,
610
+ "grad_norm": 0.9694421291351318,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 2.5367,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.02276684076603723,
617
+ "grad_norm": 0.8392857313156128,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 2.5764,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02303468595152002,
624
+ "grad_norm": 0.8242656588554382,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 2.6456,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.023302531137002813,
631
+ "grad_norm": 0.8404006361961365,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 2.6333,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.023570376322485605,
638
+ "grad_norm": 0.8129677176475525,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 2.4716,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.023838221507968393,
645
+ "grad_norm": 0.8945534229278564,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 2.735,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.024106066693451184,
652
+ "grad_norm": 1.0124059915542603,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 2.4661,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.024373911878933976,
659
+ "grad_norm": 0.9415590763092041,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 2.6995,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.024641757064416767,
666
+ "grad_norm": 0.9964925050735474,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 2.8116,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.02490960224989956,
673
+ "grad_norm": 1.066971778869629,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 2.6927,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.02517744743538235,
680
+ "grad_norm": 1.2569211721420288,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 2.854,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02544529262086514,
687
+ "grad_norm": 1.2050228118896484,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 2.9013,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02571313780634793,
694
+ "grad_norm": 1.1754610538482666,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 3.065,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02598098299183072,
701
+ "grad_norm": 1.2249592542648315,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 3.0228,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.026248828177313513,
708
+ "grad_norm": 1.3605834245681763,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 3.2149,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.026516673362796304,
715
+ "grad_norm": 1.7343082427978516,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 3.5295,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.026784518548279096,
722
+ "grad_norm": 2.0806899070739746,
723
+ "learning_rate": 0.0,
724
+ "loss": 3.9887,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.026784518548279096,
729
+ "eval_loss": 2.29975962638855,
730
+ "eval_runtime": 214.2069,
731
+ "eval_samples_per_second": 29.355,
732
+ "eval_steps_per_second": 3.669,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.164980962656256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null